* [PATCH v8 1/3] mm: add new api to enable ksm per process
2023-04-15 22:59 [PATCH v8 0/3] mm: process/cgroup ksm support Stefan Roesch
@ 2023-04-15 22:59 ` Stefan Roesch
2023-04-17 15:00 ` David Hildenbrand
2023-04-15 22:59 ` [PATCH v8 2/3] mm: add new KSM process and sysfs knobs Stefan Roesch
2023-04-15 22:59 ` [PATCH v8 3/3] selftests/mm: add new selftests for KSM Stefan Roesch
2 siblings, 1 reply; 11+ messages in thread
From: Stefan Roesch @ 2023-04-15 22:59 UTC (permalink / raw)
To: kernel-team
Cc: shr, linux-mm, riel, mhocko, david, linux-kselftest, linux-doc,
akpm, hannes, willy, Bagas Sanjaya
So far KSM can only be enabled by calling madvise for memory regions. To
be able to use KSM for more workloads, KSM needs to have the ability to be
enabled / disabled at the process / cgroup level.
1. New options for prctl system command
This patch series adds two new options to the prctl system call.
The first one allows to enable KSM at the process level and the second
one to query the setting.
The setting will be inherited by child processes.
With the above setting, KSM can be enabled for the seed process of a
cgroup and all processes in the cgroup will inherit the setting.
2. Changes to KSM processing
When KSM is enabled at the process level, the KSM code will iterate
over all the VMA's and enable KSM for the eligible VMA's.
When forking a process that has KSM enabled, the setting will be
inherited by the new child process.
1) Introduce new MMF_VM_MERGE_ANY flag
This introduces the new flag MMF_VM_MERGE_ANY flag. When this flag
is set, kernel samepage merging (ksm) gets enabled for all vma's of a
process.
2) Setting VM_MERGEABLE on VMA creation
When a VMA is created, if the MMF_VM_MERGE_ANY flag is set, the
VM_MERGEABLE flag will be set for this VMA.
3) support disabling of ksm for a process
This adds the ability to disable ksm for a process if ksm has been
enabled for the process with prctl.
4) add new prctl option to get and set ksm for a process
This adds two new options to the prctl system call
- enable ksm for all vmas of a process (if the vmas support it).
- query if ksm has been enabled for a process.
3. Disabling MMF_VM_MERGE_ANY for storage keys in s390
In the s390 architecture when storage keys are used, the
MMF_VM_MERGE_ANY will be disabled.
Signed-off-by: Stefan Roesch <shr@devkernel.io>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/s390/mm/gmap.c | 7 +++
include/linux/ksm.h | 21 ++++++-
include/linux/sched/coredump.h | 1 +
include/uapi/linux/prctl.h | 2 +
kernel/sys.c | 27 +++++++++
mm/ksm.c | 106 +++++++++++++++++++++++++++------
mm/mmap.c | 3 +
7 files changed, 148 insertions(+), 19 deletions(-)
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 5a716bdcba05..0949811761e6 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2591,6 +2591,13 @@ int gmap_mark_unmergeable(void)
int ret;
VMA_ITERATOR(vmi, mm, 0);
+ /*
+ * Make sure to disable KSM (if enabled for the whole process or
+ * individual VMAs). Note that nothing currently hinders user space
+ * from re-enabling it.
+ */
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+
for_each_vma(vmi, vma) {
/* Copy vm_flags to avoid partial modifications in ksm_madvise */
vm_flags = vma->vm_flags;
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 7e232ba59b86..fa996373653b 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -18,13 +18,26 @@
#ifdef CONFIG_KSM
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags);
+
+void ksm_add_vma(struct vm_area_struct *vma);
+int ksm_enable_merge_any(struct mm_struct *mm);
+
int __ksm_enter(struct mm_struct *mm);
void __ksm_exit(struct mm_struct *mm);
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
- if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
- return __ksm_enter(mm);
+ int ret;
+
+ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) {
+ ret = __ksm_enter(mm);
+ if (ret)
+ return ret;
+ }
+
+ if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags))
+ set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+
return 0;
}
@@ -53,6 +66,10 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
#else /* !CONFIG_KSM */
+static inline void ksm_add_vma(struct vm_area_struct *vma)
+{
+}
+
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
return 0;
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 0e17ae7fbfd3..0ee96ea7a0e9 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
+#define MMF_VM_MERGE_ANY 29
#endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index b99c0be72577..f23d9a16507f 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -292,4 +292,6 @@ struct prctl_mm_map {
#define PR_GET_AUXV 0x41555856
+#define PR_SET_MEMORY_MERGE 67
+#define PR_GET_MEMORY_MERGE 68
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 26c1399e0654..72cdb16e2636 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -15,6 +15,7 @@
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/kmod.h>
+#include <linux/ksm.h>
#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.h>
@@ -2687,6 +2688,32 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SET_VMA:
error = prctl_set_vma(arg2, arg3, arg4, arg5);
break;
+#ifdef CONFIG_KSM
+ case PR_SET_MEMORY_MERGE:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ if (mmap_write_lock_killable(me->mm))
+ return -EINTR;
+
+ if (arg2) {
+ error = ksm_enable_merge_any(me->mm);
+ } else {
+ /*
+ * TODO: we might want disable KSM on all VMAs and
+ * trigger unsharing to completely disable KSM.
+ */
+ clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+ error = 0;
+ }
+ mmap_write_unlock(me->mm);
+ break;
+ case PR_GET_MEMORY_MERGE:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+ break;
+#endif
default:
error = -EINVAL;
break;
diff --git a/mm/ksm.c b/mm/ksm.c
index 290a3eb6d8de..1c81e4408af1 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -515,6 +515,28 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}
+static bool vma_ksm_compatible(struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP |
+ VM_IO | VM_DONTEXPAND | VM_HUGETLB |
+ VM_MIXEDMAP))
+ return false; /* just ignore the advice */
+
+ if (vma_is_dax(vma))
+ return false;
+
+#ifdef VM_SAO
+ if (vma->vm_flags & VM_SAO)
+ return false;
+#endif
+#ifdef VM_SPARC_ADI
+ if (vma->vm_flags & VM_SPARC_ADI)
+ return false;
+#endif
+
+ return true;
+}
+
static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
unsigned long addr)
{
@@ -1026,6 +1048,7 @@ static int unmerge_and_remove_all_rmap_items(void)
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
mmdrop(mm);
} else
spin_unlock(&ksm_mmlist_lock);
@@ -2408,6 +2431,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
mmap_read_unlock(mm);
mmdrop(mm);
} else {
@@ -2485,6 +2509,68 @@ static int ksm_scan_thread(void *nothing)
return 0;
}
+static void __ksm_add_vma(struct vm_area_struct *vma)
+{
+ unsigned long vm_flags = vma->vm_flags;
+
+ if (vm_flags & VM_MERGEABLE)
+ return;
+
+ if (vma_ksm_compatible(vma)) {
+ vm_flags |= VM_MERGEABLE;
+ vm_flags_reset(vma, vm_flags);
+ }
+}
+
+/**
+ * ksm_add_vma - Mark vma as mergeable if compatible
+ *
+ * @vma: Pointer to vma
+ */
+void ksm_add_vma(struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
+
+ if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+ __ksm_add_vma(vma);
+}
+
+static void ksm_add_vmas(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+
+ VMA_ITERATOR(vmi, mm, 0);
+ for_each_vma(vmi, vma)
+ __ksm_add_vma(vma);
+}
+
+/**
+ * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all
+ * compatible VMA's
+ *
+ * @mm: Pointer to mm
+ *
+ * Returns 0 on success, otherwise error code
+ */
+int ksm_enable_merge_any(struct mm_struct *mm)
+{
+ int err;
+
+ if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+ return 0;
+
+ if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+ err = __ksm_enter(mm);
+ if (err)
+ return err;
+ }
+
+ set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+ ksm_add_vmas(mm);
+
+ return 0;
+}
+
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags)
{
@@ -2493,25 +2579,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
switch (advice) {
case MADV_MERGEABLE:
- /*
- * Be somewhat over-protective for now!
- */
- if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE |
- VM_PFNMAP | VM_IO | VM_DONTEXPAND |
- VM_HUGETLB | VM_MIXEDMAP))
- return 0; /* just ignore the advice */
-
- if (vma_is_dax(vma))
+ if (vma->vm_flags & VM_MERGEABLE)
return 0;
-
-#ifdef VM_SAO
- if (*vm_flags & VM_SAO)
+ if (!vma_ksm_compatible(vma))
return 0;
-#endif
-#ifdef VM_SPARC_ADI
- if (*vm_flags & VM_SPARC_ADI)
- return 0;
-#endif
if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
err = __ksm_enter(mm);
@@ -2615,6 +2686,7 @@ void __ksm_exit(struct mm_struct *mm)
if (easy_to_free) {
mm_slot_free(mm_slot_cache, mm_slot);
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
mmdrop(mm);
} else if (mm_slot) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 51cd747884e3..10e573535380 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -46,6 +46,7 @@
#include <linux/pkeys.h>
#include <linux/oom.h>
#include <linux/sched/mm.h>
+#include <linux/ksm.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
@@ -2691,6 +2692,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
if (file && vm_flags & VM_SHARED)
mapping_unmap_writable(file->f_mapping);
file = vma->vm_file;
+ ksm_add_vma(vma);
expanded:
perf_event_mmap(vma);
@@ -2963,6 +2965,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
goto mas_store_fail;
mm->map_count++;
+ ksm_add_vma(vma);
out:
perf_event_mmap(vma);
mm->total_vm += len >> PAGE_SHIFT;
--
2.31.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v8 3/3] selftests/mm: add new selftests for KSM
2023-04-15 22:59 [PATCH v8 0/3] mm: process/cgroup ksm support Stefan Roesch
2023-04-15 22:59 ` [PATCH v8 1/3] mm: add new api to enable ksm per process Stefan Roesch
2023-04-15 22:59 ` [PATCH v8 2/3] mm: add new KSM process and sysfs knobs Stefan Roesch
@ 2023-04-15 22:59 ` Stefan Roesch
2023-04-17 8:07 ` David Hildenbrand
2023-04-17 14:35 ` David Hildenbrand
2 siblings, 2 replies; 11+ messages in thread
From: Stefan Roesch @ 2023-04-15 22:59 UTC (permalink / raw)
To: kernel-team
Cc: shr, linux-mm, riel, mhocko, david, linux-kselftest, linux-doc,
akpm, hannes, willy, Bagas Sanjaya
This adds three new tests to the selftests for KSM. These tests use the
new prctl API's to enable and disable KSM.
1) add new prctl flags to prctl header file in tools dir
This adds the new prctl flags to the include file prct.h in the
tools directory. This makes sure they are available for testing.
2) add KSM prctl merge test to ksm_tests
This adds the -t option to the ksm_tests program. The -t flag
allows to specify if it should use madvise or prctl ksm merging.
3) add two functions for debugging merge outcome for ksm_tests
This adds two functions to report the metrics in /proc/self/ksm_stat
and /sys/kernel/debug/mm/ksm. The debug output is enabled with the
-d option.
4) add KSM prctl test to ksm_functional_tests
This adds a test to the ksm_functional_test that verifies that the
prctl system call to enable / disable KSM works.
5) add KSM fork test to ksm_functional_test
Add fork test to verify that the MMF_VM_MERGE_ANY flag is inherited
by the child process.
Signed-off-by: Stefan Roesch <shr@devkernel.io>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
tools/include/uapi/linux/prctl.h | 2 +
tools/testing/selftests/mm/Makefile | 2 +-
.../selftests/mm/ksm_functional_tests.c | 90 ++++++++-
tools/testing/selftests/mm/ksm_tests.c | 172 ++++++++++++++----
4 files changed, 227 insertions(+), 39 deletions(-)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 1312a137f7fb..759b3f53e53f 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -290,4 +290,6 @@ struct prctl_mm_map {
#define PR_SET_VMA 0x53564d41
# define PR_SET_VMA_ANON_NAME 0
+#define PR_SET_MEMORY_MERGE 67
+#define PR_GET_MEMORY_MERGE 68
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 5a3434419403..65814bdcaa0c 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -29,7 +29,7 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p
# LDLIBS.
MAKEFLAGS += --no-builtin-rules
-CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
+CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/tools/include/uapi $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
LDLIBS = -lrt -lpthread
TEST_GEN_PROGS = cow
diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index d3f26050dfd7..4f02ba112ec5 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -15,8 +15,10 @@
#include <errno.h>
#include <fcntl.h>
#include <sys/mman.h>
+#include <sys/prctl.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
+#include <sys/wait.h>
#include <linux/userfaultfd.h>
#include "../kselftest.h"
@@ -237,9 +239,92 @@ static void test_unmerge_uffd_wp(void)
}
#endif
+/* Verify that KSM can be enabled / queried with prctl. */
+static void test_prctl(void)
+{
+ int ret;
+
+ ksft_print_msg("[RUN] %s\n", __func__);
+
+ ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0);
+ if (ret < 0 && errno == EINVAL) {
+ ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n");
+ return;
+ } else if (ret) {
+ ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n");
+ }
+
+ ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0);
+ if (ret < 0) {
+ ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n");
+ return;
+ } else if (ret != 1) {
+ ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 not effective\n");
+ return;
+ }
+
+ ret = prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0);
+ if (ret) {
+ ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n");
+ return;
+ }
+
+ ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0);
+ if (ret < 0) {
+ ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n");
+ return;
+ } else if (ret != 0) {
+ ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 not effective\n");
+ return;
+ }
+
+ ksft_test_result_pass("Setting/clearing PR_SET_MEMORY_MERGE works\n");
+}
+
+/* Verify that prctl ksm flag is inherited. */
+static void test_prctl_fork(void)
+{
+ int ret, status;
+ pid_t child_pid;
+
+ ksft_print_msg("[RUN] %s\n", __func__);
+
+ ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0);
+ if (ret < 0 && errno == EINVAL) {
+ ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n");
+ return;
+ } else if (ret) {
+ ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n");
+ return;
+ }
+
+ child_pid = fork();
+ if (!child_pid) {
+ exit(prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0));
+ } else if (child_pid < 0) {
+ ksft_test_result_fail("fork() failed\n");
+ return;
+ }
+
+ if (waitpid(child_pid, &status, 0) < 0) {
+ ksft_test_result_fail("waitpid() failed\n");
+ return;
+ } else if (WEXITSTATUS(status) != 1) {
+ ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n");
+ return;
+ }
+
+ if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) {
+ ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n");
+ return;
+ }
+
+ ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n");
+}
+
int main(int argc, char **argv)
{
- unsigned int tests = 2;
+ unsigned int tests = 4;
int err;
#ifdef __NR_userfaultfd
@@ -267,6 +352,9 @@ int main(int argc, char **argv)
test_unmerge_uffd_wp();
#endif
+ test_prctl();
+ test_prctl_fork();
+
err = ksft_get_fail_cnt();
if (err)
ksft_exit_fail_msg("%d out of %d tests failed\n",
diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
index 74281593a124..a3145ce868df 100644
--- a/tools/testing/selftests/mm/ksm_tests.c
+++ b/tools/testing/selftests/mm/ksm_tests.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
#include <stdbool.h>
#include <time.h>
#include <string.h>
@@ -21,6 +23,7 @@
#define KSM_PROT_STR_DEFAULT "rw"
#define KSM_USE_ZERO_PAGES_DEFAULT false
#define KSM_MERGE_ACROSS_NODES_DEFAULT true
+#define KSM_MERGE_TYPE_DEFAULT 0
#define MB (1ul << 20)
struct ksm_sysfs {
@@ -33,9 +36,16 @@ struct ksm_sysfs {
unsigned long use_zero_pages;
};
+enum ksm_merge_type {
+ KSM_MERGE_MADVISE,
+ KSM_MERGE_PRCTL,
+ KSM_MERGE_LAST = KSM_MERGE_PRCTL
+};
+
enum ksm_test_name {
CHECK_KSM_MERGE,
CHECK_KSM_UNMERGE,
+ CHECK_KSM_GET_MERGE_TYPE,
CHECK_KSM_ZERO_PAGE_MERGE,
CHECK_KSM_NUMA_MERGE,
KSM_MERGE_TIME,
@@ -44,6 +54,8 @@ enum ksm_test_name {
KSM_COW_TIME
};
+int debug = 0;
+
static int ksm_write_sysfs(const char *file_path, unsigned long val)
{
FILE *f = fopen(file_path, "w");
@@ -82,6 +94,53 @@ static int ksm_read_sysfs(const char *file_path, unsigned long *val)
return 0;
}
+static void ksm_print_sysfs(void)
+{
+ unsigned long max_page_sharing, pages_sharing, pages_shared;
+ unsigned long full_scans, pages_unshared, pages_volatile;
+ unsigned long stable_node_chains, stable_node_dups;
+ long general_profit;
+
+ if (ksm_read_sysfs(KSM_FP("pages_shared"), &pages_shared) ||
+ ksm_read_sysfs(KSM_FP("pages_sharing"), &pages_sharing) ||
+ ksm_read_sysfs(KSM_FP("max_page_sharing"), &max_page_sharing) ||
+ ksm_read_sysfs(KSM_FP("full_scans"), &full_scans) ||
+ ksm_read_sysfs(KSM_FP("pages_unshared"), &pages_unshared) ||
+ ksm_read_sysfs(KSM_FP("pages_volatile"), &pages_volatile) ||
+ ksm_read_sysfs(KSM_FP("stable_node_chains"), &stable_node_chains) ||
+ ksm_read_sysfs(KSM_FP("stable_node_dups"), &stable_node_dups) ||
+ ksm_read_sysfs(KSM_FP("general_profit"), (unsigned long *)&general_profit))
+ return;
+
+ printf("pages_shared : %lu\n", pages_shared);
+ printf("pages_sharing : %lu\n", pages_sharing);
+ printf("max_page_sharing : %lu\n", max_page_sharing);
+ printf("full_scans : %lu\n", full_scans);
+ printf("pages_unshared : %lu\n", pages_unshared);
+ printf("pages_volatile : %lu\n", pages_volatile);
+ printf("stable_node_chains: %lu\n", stable_node_chains);
+ printf("stable_node_dups : %lu\n", stable_node_dups);
+ printf("general_profit : %ld\n", general_profit);
+}
+
+static void ksm_print_procfs(void)
+{
+ const char *file_name = "/proc/self/ksm_stat";
+ char buffer[512];
+ FILE *f = fopen(file_name, "r");
+
+ if (!f) {
+ fprintf(stderr, "f %s\n", file_name);
+ perror("fopen");
+ return;
+ }
+
+ while (fgets(buffer, sizeof(buffer), f))
+ printf("%s", buffer);
+
+ fclose(f);
+}
+
static int str_to_prot(char *prot_str)
{
int prot = 0;
@@ -128,7 +187,12 @@ static void print_help(void)
" Default: %d\n", KSM_USE_ZERO_PAGES_DEFAULT);
printf(" -m: change merge_across_nodes tunable\n"
" Default: %d\n", KSM_MERGE_ACROSS_NODES_DEFAULT);
+ printf(" -d: turn debugging output on\n");
printf(" -s: the size of duplicated memory area (in MiB)\n");
+ printf(" -t: KSM merge type\n"
+ " Default: 0\n"
+ " 0: madvise merging\n"
+ " 1: prctl merging\n");
exit(0);
}
@@ -176,12 +240,21 @@ static int ksm_do_scan(int scan_count, struct timespec start_time, int timeout)
return 0;
}
-static int ksm_merge_pages(void *addr, size_t size, struct timespec start_time, int timeout)
+static int ksm_merge_pages(int merge_type, void *addr, size_t size,
+ struct timespec start_time, int timeout)
{
- if (madvise(addr, size, MADV_MERGEABLE)) {
- perror("madvise");
- return 1;
+ if (merge_type == KSM_MERGE_MADVISE) {
+ if (madvise(addr, size, MADV_MERGEABLE)) {
+ perror("madvise");
+ return 1;
+ }
+ } else if (merge_type == KSM_MERGE_PRCTL) {
+ if (prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0)) {
+ perror("prctl");
+ return 1;
+ }
}
+
if (ksm_write_sysfs(KSM_FP("run"), 1))
return 1;
@@ -211,6 +284,11 @@ static bool assert_ksm_pages_count(long dupl_page_count)
ksm_read_sysfs(KSM_FP("max_page_sharing"), &max_page_sharing))
return false;
+ if (debug) {
+ ksm_print_sysfs();
+ ksm_print_procfs();
+ }
+
/*
* Since there must be at least 2 pages for merging and 1 page can be
* shared with the limited number of pages (max_page_sharing), sometimes
@@ -266,7 +344,8 @@ static int ksm_restore(struct ksm_sysfs *ksm_sysfs)
return 0;
}
-static int check_ksm_merge(int mapping, int prot, long page_count, int timeout, size_t page_size)
+static int check_ksm_merge(int merge_type, int mapping, int prot,
+ long page_count, int timeout, size_t page_size)
{
void *map_ptr;
struct timespec start_time;
@@ -281,13 +360,15 @@ static int check_ksm_merge(int mapping, int prot, long page_count, int timeout,
if (!map_ptr)
return KSFT_FAIL;
- if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout))
goto err_out;
/* verify that the right number of pages are merged */
if (assert_ksm_pages_count(page_count)) {
printf("OK\n");
munmap(map_ptr, page_size * page_count);
+ if (merge_type == KSM_MERGE_PRCTL)
+ prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0);
return KSFT_PASS;
}
@@ -297,7 +378,7 @@ static int check_ksm_merge(int mapping, int prot, long page_count, int timeout,
return KSFT_FAIL;
}
-static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_size)
+static int check_ksm_unmerge(int merge_type, int mapping, int prot, int timeout, size_t page_size)
{
void *map_ptr;
struct timespec start_time;
@@ -313,7 +394,7 @@ static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_siz
if (!map_ptr)
return KSFT_FAIL;
- if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout))
goto err_out;
/* change 1 byte in each of the 2 pages -- KSM must automatically unmerge them */
@@ -337,8 +418,8 @@ static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_siz
return KSFT_FAIL;
}
-static int check_ksm_zero_page_merge(int mapping, int prot, long page_count, int timeout,
- bool use_zero_pages, size_t page_size)
+static int check_ksm_zero_page_merge(int merge_type, int mapping, int prot, long page_count,
+ int timeout, bool use_zero_pages, size_t page_size)
{
void *map_ptr;
struct timespec start_time;
@@ -356,7 +437,7 @@ static int check_ksm_zero_page_merge(int mapping, int prot, long page_count, int
if (!map_ptr)
return KSFT_FAIL;
- if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout))
goto err_out;
/*
@@ -402,8 +483,8 @@ static int get_first_mem_node(void)
return get_next_mem_node(numa_max_node());
}
-static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_across_nodes,
- size_t page_size)
+static int check_ksm_numa_merge(int merge_type, int mapping, int prot, int timeout,
+ bool merge_across_nodes, size_t page_size)
{
void *numa1_map_ptr, *numa2_map_ptr;
struct timespec start_time;
@@ -439,8 +520,8 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a
memset(numa2_map_ptr, '*', page_size);
/* try to merge the pages */
- if (ksm_merge_pages(numa1_map_ptr, page_size, start_time, timeout) ||
- ksm_merge_pages(numa2_map_ptr, page_size, start_time, timeout))
+ if (ksm_merge_pages(merge_type, numa1_map_ptr, page_size, start_time, timeout) ||
+ ksm_merge_pages(merge_type, numa2_map_ptr, page_size, start_time, timeout))
goto err_out;
/*
@@ -466,7 +547,8 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a
return KSFT_FAIL;
}
-static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size)
+static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot,
+ int timeout, size_t map_size)
{
void *map_ptr, *map_ptr_orig;
struct timespec start_time, end_time;
@@ -508,7 +590,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m
perror("clock_gettime");
goto err_out;
}
- if (ksm_merge_pages(map_ptr, map_size, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout))
goto err_out;
if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) {
perror("clock_gettime");
@@ -533,7 +615,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m
return KSFT_FAIL;
}
-static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size)
+static int ksm_merge_time(int merge_type, int mapping, int prot, int timeout, size_t map_size)
{
void *map_ptr;
struct timespec start_time, end_time;
@@ -549,7 +631,7 @@ static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size)
perror("clock_gettime");
goto err_out;
}
- if (ksm_merge_pages(map_ptr, map_size, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout))
goto err_out;
if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) {
perror("clock_gettime");
@@ -574,7 +656,7 @@ static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size)
return KSFT_FAIL;
}
-static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size)
+static int ksm_unmerge_time(int merge_type, int mapping, int prot, int timeout, size_t map_size)
{
void *map_ptr;
struct timespec start_time, end_time;
@@ -589,7 +671,7 @@ static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size)
perror("clock_gettime");
goto err_out;
}
- if (ksm_merge_pages(map_ptr, map_size, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout))
goto err_out;
if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
@@ -621,7 +703,7 @@ static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size)
return KSFT_FAIL;
}
-static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size)
+static int ksm_cow_time(int merge_type, int mapping, int prot, int timeout, size_t page_size)
{
void *map_ptr;
struct timespec start_time, end_time;
@@ -660,7 +742,7 @@ static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size)
memset(map_ptr + page_size * i, '+', i / 2 + 1);
memset(map_ptr + page_size * (i + 1), '+', i / 2 + 1);
}
- if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout))
+ if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout))
goto err_out;
if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
@@ -697,6 +779,7 @@ int main(int argc, char *argv[])
int ret, opt;
int prot = 0;
int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT;
+ int merge_type = KSM_MERGE_TYPE_DEFAULT;
long page_count = KSM_PAGE_COUNT_DEFAULT;
size_t page_size = sysconf(_SC_PAGESIZE);
struct ksm_sysfs ksm_sysfs_old;
@@ -705,7 +788,7 @@ int main(int argc, char *argv[])
bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT;
long size_MB = 0;
- while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCHD")) != -1) {
+ while ((opt = getopt(argc, argv, "dha:p:l:z:m:s:t:MUZNPCHD")) != -1) {
switch (opt) {
case 'a':
prot = str_to_prot(optarg);
@@ -739,12 +822,26 @@ int main(int argc, char *argv[])
else
merge_across_nodes = 1;
break;
+ case 'd':
+ debug = 1;
+ break;
case 's':
size_MB = atoi(optarg);
if (size_MB <= 0) {
printf("Size must be greater than 0\n");
return KSFT_FAIL;
}
+ case 't':
+ {
+ int tmp = atoi(optarg);
+
+ if (tmp < 0 || tmp > KSM_MERGE_LAST) {
+ printf("Invalid merge type\n");
+ return KSFT_FAIL;
+ }
+ merge_type = tmp;
+ }
+ break;
case 'M':
break;
case 'U':
@@ -795,35 +892,36 @@ int main(int argc, char *argv[])
switch (test_name) {
case CHECK_KSM_MERGE:
- ret = check_ksm_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count,
+ ret = check_ksm_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count,
ksm_scan_limit_sec, page_size);
break;
case CHECK_KSM_UNMERGE:
- ret = check_ksm_unmerge(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
- page_size);
+ ret = check_ksm_unmerge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ ksm_scan_limit_sec, page_size);
break;
case CHECK_KSM_ZERO_PAGE_MERGE:
- ret = check_ksm_zero_page_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count,
- ksm_scan_limit_sec, use_zero_pages, page_size);
+ ret = check_ksm_zero_page_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ page_count, ksm_scan_limit_sec, use_zero_pages,
+ page_size);
break;
case CHECK_KSM_NUMA_MERGE:
- ret = check_ksm_numa_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
- merge_across_nodes, page_size);
+ ret = check_ksm_numa_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ ksm_scan_limit_sec, merge_across_nodes, page_size);
break;
case KSM_MERGE_TIME:
if (size_MB == 0) {
printf("Option '-s' is required.\n");
return KSFT_FAIL;
}
- ret = ksm_merge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
- size_MB);
+ ret = ksm_merge_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ ksm_scan_limit_sec, size_MB);
break;
case KSM_MERGE_TIME_HUGE_PAGES:
if (size_MB == 0) {
printf("Option '-s' is required.\n");
return KSFT_FAIL;
}
- ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ ret = ksm_merge_hugepages_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
ksm_scan_limit_sec, size_MB);
break;
case KSM_UNMERGE_TIME:
@@ -831,12 +929,12 @@ int main(int argc, char *argv[])
printf("Option '-s' is required.\n");
return KSFT_FAIL;
}
- ret = ksm_unmerge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ ret = ksm_unmerge_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
ksm_scan_limit_sec, size_MB);
break;
case KSM_COW_TIME:
- ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
- page_size);
+ ret = ksm_cow_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot,
+ ksm_scan_limit_sec, page_size);
break;
}
--
2.31.1
^ permalink raw reply related [flat|nested] 11+ messages in thread